
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)
=> Add worker ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.RandomSmallWorldGraph object at 0x7f673ae91400>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3054 top1= 10.0000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([0, 0, 0, 0, 0], device='cuda:0')
Worker 1 has targets: tensor([1, 1, 1, 1, 1], device='cuda:0')
Worker 2 has targets: tensor([1, 2, 2, 2, 2], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 3, 3, 3], device='cuda:0')
Worker 4 has targets: tensor([3, 4, 4, 4, 4], device='cuda:0')
Worker 5 has targets: tensor([4, 5, 5, 5, 5], device='cuda:0')
Worker 6 has targets: tensor([6, 6, 6, 6, 6], device='cuda:0')
Worker 7 has targets: tensor([7, 7, 7, 7, 7], device='cuda:0')
Worker 8 has targets: tensor([7, 8, 8, 8, 8], device='cuda:0')
Worker 9 has targets: tensor([8, 9, 9, 9, 9], device='cuda:0')
Worker 10 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 11 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')



=== Log global consensus distance @ E1B0 ===
consensus_distance=0.001



=== Log average shortest path distance for small world @ E1B0 ===
2.7777777777777777


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.1676 top1= 94.0625
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0968 top1= 98.1250
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.0743 top1= 97.5000
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.0737 top1= 97.8125
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.0677 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0316 top1= 65.3646

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1401 top1= 97.1875

=== Log global consensus distance @ E2B0 ===
consensus_distance=0.166


[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0413 top1= 99.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0479 top1= 98.1250
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.0481 top1= 98.4375
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.0692 top1= 97.8125
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0505 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7462 top1= 74.9299

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0882 top1= 97.8125

=== Log global consensus distance @ E3B0 ===
consensus_distance=0.078


[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0365 top1= 99.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0246 top1= 99.6875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0497 top1= 98.7500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0596 top1= 97.8125
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0477 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6648 top1= 77.3938

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0762 top1= 98.4375

=== Log global consensus distance @ E4B0 ===
consensus_distance=0.061


[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0468 top1= 98.7500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0211 top1= 99.3750
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0300 top1= 99.6875
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0427 top1= 98.7500
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0404 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6132 top1= 78.9864

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0738 top1= 98.4375

=== Log global consensus distance @ E5B0 ===
consensus_distance=0.055


[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0378 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0242 top1= 99.3750
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0197 top1= 99.6875
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0665 top1= 98.4375
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0352 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5805 top1= 80.5288

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0655 top1= 98.4375

=== Log global consensus distance @ E6B0 ===
consensus_distance=0.048


[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0273 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0174 top1= 99.6875
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0157 top1=100.0000
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0695 top1= 98.7500
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0593 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5968 top1= 79.5172

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0637 top1= 98.4375

=== Log global consensus distance @ E7B0 ===
consensus_distance=0.051


[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0250 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0408 top1= 98.7500
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0211 top1= 99.6875
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0542 top1= 98.7500
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0331 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5751 top1= 80.3385

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0592 top1= 99.3750

=== Log global consensus distance @ E8B0 ===
consensus_distance=0.044


[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0285 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0222 top1= 99.3750
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0157 top1= 99.6875
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0558 top1= 98.7500
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0324 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5750 top1= 80.5589

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0521 top1= 98.7500

=== Log global consensus distance @ E9B0 ===
consensus_distance=0.042


[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0433 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0162 top1= 99.3750
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0218 top1= 99.0625
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0371 top1= 98.7500
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0371 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5785 top1= 80.8794

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0789 top1= 98.1250

=== Log global consensus distance @ E10B0 ===
consensus_distance=0.047


[E10B10 |   4224/60000 (  7%) ] Loss: 0.0191 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0256 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0344 top1= 99.0625
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0429 top1= 98.7500
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0313 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5862 top1= 80.4487

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0676 top1= 98.7500

=== Log global consensus distance @ E11B0 ===
consensus_distance=0.044


[E11B10 |   4224/60000 (  7%) ] Loss: 0.0194 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0226 top1= 99.6875
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0212 top1= 99.3750
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0375 top1= 99.0625
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0301 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5994 top1= 79.8878

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0715 top1= 98.7500

=== Log global consensus distance @ E12B0 ===
consensus_distance=0.042


[E12B10 |   4224/60000 (  7%) ] Loss: 0.0230 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0176 top1= 99.6875
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0266 top1= 99.0625
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0403 top1= 98.7500
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0309 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6028 top1= 80.2885

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0643 top1= 98.7500

=== Log global consensus distance @ E13B0 ===
consensus_distance=0.043


[E13B10 |   4224/60000 (  7%) ] Loss: 0.0215 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0125 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0234 top1= 99.3750
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0335 top1= 99.6875
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0292 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6258 top1= 79.1266

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0711 top1= 98.7500

=== Log global consensus distance @ E14B0 ===
consensus_distance=0.044


[E14B10 |   4224/60000 (  7%) ] Loss: 0.0256 top1= 99.3750
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0166 top1= 99.6875
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0446 top1= 99.0625
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0417 top1= 99.0625
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0292 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6455 top1= 79.4571

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0759 top1= 98.4375

=== Log global consensus distance @ E15B0 ===
consensus_distance=0.044


[E15B10 |   4224/60000 (  7%) ] Loss: 0.0261 top1= 99.3750
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0186 top1= 99.6875
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0291 top1= 99.6875
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0418 top1= 98.7500
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0297 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6595 top1= 79.3269

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0731 top1= 98.4375

=== Log global consensus distance @ E16B0 ===
consensus_distance=0.044


[E16B10 |   4224/60000 (  7%) ] Loss: 0.0276 top1= 99.3750
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0204 top1= 99.3750
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0307 top1= 99.6875
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0402 top1= 98.7500
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0278 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6869 top1= 78.7059

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0770 top1= 98.4375

=== Log global consensus distance @ E17B0 ===
consensus_distance=0.044


[E17B10 |   4224/60000 (  7%) ] Loss: 0.0486 top1= 99.3750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0222 top1= 99.6875
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0279 top1= 99.6875
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0371 top1= 99.3750
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0428 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7385 top1= 77.0933

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0712 top1= 98.1250

=== Log global consensus distance @ E18B0 ===
consensus_distance=0.052


[E18B10 |   4224/60000 (  7%) ] Loss: 0.0224 top1= 99.6875
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0185 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0416 top1= 99.3750
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0405 top1= 99.0625
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0301 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7363 top1= 78.4355

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0669 top1= 98.7500

=== Log global consensus distance @ E19B0 ===
consensus_distance=0.045


[E19B10 |   4224/60000 (  7%) ] Loss: 0.0211 top1= 99.6875
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0451 top1= 99.3750
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0441 top1= 99.0625
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0303 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7526 top1= 78.0849

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0644 top1= 97.8125

=== Log global consensus distance @ E20B0 ===
consensus_distance=0.045


[E20B10 |   4224/60000 (  7%) ] Loss: 0.0209 top1= 99.6875
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0329 top1= 99.3750
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0350 top1= 99.0625
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0416 top1= 98.7500
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0328 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7827 top1= 76.7728

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0769 top1= 97.8125

=== Log global consensus distance @ E21B0 ===
consensus_distance=0.048


[E21B10 |   4224/60000 (  7%) ] Loss: 0.0604 top1= 99.3750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.3750
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0322 top1= 99.0625
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0444 top1= 98.1250
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0287 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7973 top1= 76.7628

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0713 top1= 97.8125

=== Log global consensus distance @ E22B0 ===
consensus_distance=0.047


[E22B10 |   4224/60000 (  7%) ] Loss: 0.0306 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0222 top1= 99.3750
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0315 top1= 98.7500
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0427 top1= 98.4375
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0336 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8083 top1= 76.5725

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0835 top1= 97.8125

=== Log global consensus distance @ E23B0 ===
consensus_distance=0.047


[E23B10 |   4224/60000 (  7%) ] Loss: 0.0456 top1= 99.3750
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0264 top1= 99.6875
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0401 top1= 98.7500
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0360 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8189 top1= 76.3922

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0787 top1= 97.8125

=== Log global consensus distance @ E24B0 ===
consensus_distance=0.048


[E24B10 |   4224/60000 (  7%) ] Loss: 0.0285 top1= 99.3750
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0339 top1= 99.0625
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0348 top1= 99.0625
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0457 top1= 99.0625
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0303 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8321 top1= 76.4724

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0746 top1= 98.1250

=== Log global consensus distance @ E25B0 ===
consensus_distance=0.047


[E25B10 |   4224/60000 (  7%) ] Loss: 0.0883 top1= 99.0625
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0208 top1= 99.6875
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0289 top1= 99.0625
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0543 top1= 98.4375
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0362 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8610 top1= 74.7696

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0782 top1= 98.1250

=== Log global consensus distance @ E26B0 ===
consensus_distance=0.050


[E26B10 |   4224/60000 (  7%) ] Loss: 0.0322 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0240 top1= 99.6875
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0451 top1= 98.7500
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0475 top1= 98.4375
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0310 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8599 top1= 75.5008

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0875 top1= 98.1250

=== Log global consensus distance @ E27B0 ===
consensus_distance=0.048


[E27B10 |   4224/60000 (  7%) ] Loss: 0.0933 top1= 98.7500
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0185 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0278 top1= 99.3750
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0511 top1= 98.4375
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0369 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8777 top1= 74.0585

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0820 top1= 97.8125

=== Log global consensus distance @ E28B0 ===
consensus_distance=0.049


[E28B10 |   4224/60000 (  7%) ] Loss: 0.0638 top1= 99.0625
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0396 top1= 98.4375
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0468 top1= 98.7500
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0345 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8731 top1= 75.0000

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0779 top1= 97.5000

=== Log global consensus distance @ E29B0 ===
consensus_distance=0.048


[E29B10 |   4224/60000 (  7%) ] Loss: 0.0209 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0229 top1= 99.3750
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0360 top1= 99.0625
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0566 top1= 98.1250
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0346 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8904 top1= 73.4976

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0746 top1= 98.1250

=== Log global consensus distance @ E30B0 ===
consensus_distance=0.046


[E30B10 |   4224/60000 (  7%) ] Loss: 0.0646 top1= 99.0625
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0253 top1= 99.6875
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0247 top1= 99.6875
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0496 top1= 98.7500
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0362 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8970 top1= 73.8381

